Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

2026-03-07

AI Summary

This work proposes the PSAD framework to address the challenges of deploying generative reranking models in practice, where achieving both high generation quality and low-latency inference remains difficult, and user-item feature interactions are often insufficient. PSAD integrates a semi-autoregressive generation mechanism to balance ranking effectiveness with inference efficiency, employs online knowledge distillation to dynamically transfer knowledge from a teacher model to a lightweight scoring network, and introduces a user profiling module to capture dynamic interests and intents, thereby enhancing personalized interactions. Extensive experiments on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art methods in both ranking performance and inference efficiency.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.

Problem

• reranking
• generative models
• inference latency
• user-item interaction
• recommendation systems

Innovation

• Semi-Autoregressive Generation
• Online Knowledge Distillation
• Personalized Reranking
• User Profile Network
• Efficient Inference